Protein secondary structure can be regarded as an information bridge that links the primary sequence and tertiary structure. Accurate 8-state secondary structure prediction can significantly give ...more precise and high resolution on structure-based properties analysis.
We present a novel deep learning architecture which exploits an integrative synergy of prediction by a convolutional neural network, residual network, and bidirectional recurrent neural network to improve the performance of protein secondary structure prediction. A local block comprised of convolutional filters and original input is designed for capturing local sequence features. The subsequent bidirectional recurrent neural network consisting of gated recurrent units can capture global context features. Furthermore, the residual network can improve the information flow between the hidden layers and the cascaded recurrent neural network. Our proposed deep network achieved 71.4% accuracy on the benchmark CB513 dataset for the 8-state prediction; and the ensemble learning by our model achieved 74% accuracy. Our model generalization capability is also evaluated on other three independent datasets CASP10, CASP11 and CASP12 for both 8- and 3-state prediction. These prediction performances are superior to the state-of-the-art methods.
Our experiment demonstrates that it is a valuable method for predicting protein secondary structure, and capturing local and global features concurrently is very useful in deep learning.
Mussel-inspired polydopamine (PDA) modification of membrane is an effective alternative for improving permeation flux and anti-fouling performance. Meanwhile, efficient method for oil-water emulsions ...separation is still highly desired. However, problems, such as time-consuming process and low utilization ratio of expensive raw material, have always been stumbling block to application of this strategy. In this study, inkjet printing of dopamine (DA) followed by UV light irradiation to modify mussel-inspired polyvinylidene fluoride (PVDF) membrane was proposed. Accordingly, PVDF membrane was inkjet printed by alternately using DA inks and alkaline tris (hydroxymethyl) aminomethane (Tris) ink. The resultant membrane was then subjected to photopolymerization under UV irradiation to form a PDA layer. Successful formation of PDA layer on membrane surface was verified by series of physical and chemical methods. The optimized membrane (DA80-60/PVDF) exhibited superior oil/water separation performance with 1.5 times permeate flux higher than that of the pristine PVDF membrane and above 99% oil rejection rate. Meanwhile, the modified membranes showed satisfactory stability in aqueous solution with wide pH range (pH 2.0–7.0). The novel membrane modification method proposed in this study is facile, cost-saving and environment-friendly, serving as a competitive candidate for fabrication of efficient membranes for oil-water emulsion separation.
Display omitted
•A new method integrating inkjet printing of PDA and UV irradiation was proposed.•Successful formation of PDA layer on membrane surface was verified.•The optimized membrane had superior oil-water separation performance.•The proposed membrane modification method is facile, cost-saving and environment-friendly.
Graphs such as de Bruijn graphs and OLC (overlap-layout-consensus) graphs have been widely adopted for the de novo assembly of genomic short reads. This work studies another important problem in the ...field: how graphs can be used for high-performance compression of the large-scale sequencing data. We present a novel graph definition named Hamming-Shifting graph to address this problem. The definition originates from the technological characteristics of next-generation sequencing machines, aiming to link all pairs of distinct reads that have a small Hamming distance or a small shifting offset or both. We compute multiple lexicographically minimal
k
-mers to index the reads for an efficient search of the weight-lightest edges, and we prove a very high probability of successfully detecting these edges. The resulted graph creates a full mutual reference of the reads to cascade a code-minimized transfer of every child-read for an optimal compression. We conducted compression experiments on the minimum spanning forest of this extremely sparse graph, and achieved a 10 − 30% more file size reduction compared to the best compression results using existing algorithms. As future work, the separation and connectivity degrees of these giant graphs can be used as economical measurements or protocols for quick quality assessment of wet-lab machines, for sufficiency control of genomic library preparation, and for accurate de novo genome assembly.
Effectively stimulating angiogenesis and avoiding wound infection are great challenges in wound care management. Designing new healing dressings with requisite angiogenic capacity and antibacterial ...performance is of particular significance. In order to achieve this aim, we prepared a copper (Cu)-containing bioactive glass nanocoating (40-50nm) with uniform nanostructure on natural eggshell membrane (Cu-BG/ESM) by the pulsed laser deposition (PLD) technique. The surface physicochemical properties including hydrophilicity and hardness of ESM were significantly improved after depositing Cu-BG nanocoatings. Meanwhile, 5Cu-BG/ESM films containing 5mol% Cu stimulated proangiogenesis by improving vascular endothelial growth factor (VEGF) and hypoxia-inducible factor (HIF)-1α protein secretion as well as angiogenesis-related gene expression (VEGF, HIF-1α, VEGF receptor 2 (KDR) and endothelial nitric oxide (eNos)) of human umbilical vein endothelial cells (HUVECs). When used to treat full-thickness skin defects in mice, 5Cu-BG/ESM films enhanced the healing quality as confirmed by the significantly improved angiogenesis (as indicated by CD31 expression) and formation of continuous and uniform epidermis layer in vivo. Furthermore, 5Cu-BG/ESM films could maintain a sustained release of Cu(2+) ions and distinctly inhibited the viability of bacteria (Escherichia coli). The results indicate that Cu(2+) ions released from Cu-BG/ESM nanocomposite films play an important role for improving both angiogenesis and antibacterial activity and the prepared nanocomposite films combined Cu-containing BG nanocoatings with ESM are a promising biomaterial for wound healing application.
Designing new healing dressings with requisite angiogenic capacity and antibacterial performance is of particular significance in wound care management. In our study, we successfully prepared copper-containing bioactive glass/eggshell membrane (Cu-BG/ESM) nanocomposites with uniform bioactive glass nanocoatings by using pulsed laser deposition (PLD) technology. Due to the deposited Cu-BG nanocoatings on the surface of ESM, Cu-BG/ESM nanocomposites possessed significantly improved physicochemical and biological properties, including surface hydrophilicity, hardness, antibacterial ability, angiogenesis rate in vitro and wound healing quality in vivo as compared to pure ESM and BG/ESM films. Our study showed that prepared nanocoatings on Cu-BG/ESM nanocomposites offer a beneficial carrier for sustained release of Cu(2+) ions which played a key role for improving both angiogenesis and antibacterial activity. The prepared nanocomposites combined Cu-containing BG nanocoatings with ESM are a promising biomaterial for wound healing application.
Antimicrobial peptides (AMPs) are promising candidates in the fight against multidrug-resistant pathogens owing to AMPs' broad range of activities and low toxicity. Nonetheless, identification of ...AMPs through wet-lab experiments is still expensive and time consuming. Here, we propose an accurate computational method for AMP prediction by the random forest algorithm. The prediction model is based on the distribution patterns of amino acid properties along the sequence. Using our collection of large and diverse sets of AMP and non-AMP data (3268 and 166791 sequences, respectively), we evaluated 19 random forest classifiers with different positive:negative data ratios by 10-fold cross-validation. Our optimal model, AmPEP with the 1:3 data ratio, showed high accuracy (96%), Matthew's correlation coefficient (MCC) of 0.9, area under the receiver operating characteristic curve (AUC-ROC) of 0.99, and the Kappa statistic of 0.9. Descriptor analysis of AMP/non-AMP distributions by means of Pearson correlation coefficients revealed that reduced feature sets (from a full-featured set of 105 to a minimal-feature set of 23) can result in comparable performance in all respects except for some reductions in precision. Furthermore, AmPEP outperformed existing methods in terms of accuracy, MCC, and AUC-ROC when tested on benchmark datasets.
•We provide an improved Wolf Search Algorithm (WSA) using a global memory structure.•The algorithm is tested in several experiments based on 7 test problems.•Comparisons with regular WSA, ACO, and ...PSO show advantages but also limitations.•Further insights concern a suitable size of the global memory structure.
A recently proposed metaheuristics called Wolf Search Algorithm (WSA) has demonstrated its efficacy for various hard-to-solve optimization problems. In this paper, an improved version of WSA namely Eidetic-WSA with a global memory structure (GMS) or just eWSA is presented. eWSA makes use of GMS for improving its search for the optimal fitness value by preventing mediocre visited places in the search space to be visited again in future iterations. Inherited from swarm intelligence, search agents in eWSA and the traditional WSA merge into an optimal solution although the agents behave and make decisions autonomously. Heuristic information gathered from collective memory of the swarm search agents is stored in GMS. The heuristics eventually leads to faster convergence and improved optimal fitness. The concept is similar to a hybrid metaheuristics based on WSA and Tabu Search. eWSA is tested with seven standard optimization functions rigorously. In particular, eWSA is compared with two state-of-the-art metaheuristics, Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). eWSA shares some similarity with both approaches with respect to directed-random search. The similarity with ACO is, however, stronger as ACO uses pheromones as global information references that allow a balance between using previous knowledge and exploring new solutions. Under comparable experimental settings (identical population size and number of generations) eWSA is shown to outperform both ACO and PSO with statistical significance. When dedicating the same computation time, only ACO can be outperformed due to a comparably long run time per iteration of eWSA.
High throughput experiments resulted in many genomic datasets and hundreds of candidate disease genes. To discover the real disease genes from a set of candidate genes, computational methods have ...been proposed and worked on various types of genomic data sources. As a single source of genomic data is prone of bias, incompleteness and noise, integration of different genomic data sources is highly demanded to accomplish reliable disease gene identification.
In contrast to the commonly adapted data integration approach which integrates separate lists of candidate genes derived from the each single data sources, we merge various genomic networks into a multigraph which is capable of connecting multiple edges between a pair of nodes. This novel approach provides a data platform with strong noise tolerance to prioritize the disease genes. A new idea of random walk is then developed to work on multigraphs using a modified step to calculate the transition matrix. Our method is further enhanced to deal with heterogeneous data types by allowing cross-walk between phenotype and gene networks. Compared on benchmark datasets, our method is shown to be more accurate than the state-of-the-art methods in disease gene identification. We also conducted a case study to identify disease genes for Insulin-Dependent Diabetes Mellitus. Some of the newly identified disease genes are supported by recently published literature.
The proposed RWRM (Random Walk with Restart on Multigraphs) model and CHN (Complex Heterogeneous Network) model are effective in data integration for candidate gene prioritization.
The state and development of vegetation cover is an important criterion for the improvement of the ecological environment of arid regions; therefore, the study of the ecological water use of ...vegetation has become a pressing problem in ecology and hydrology. This study covered eight counties in the central and southern parts of Ningxia Hui Autonomous Region, which are located from north to south in an arid region in northwestern China. The purpose of the study was to assess the potential evaporation and environmental water consumption of local vegetation based on meteorological data, vegetation-distribution data, data on the state of water resources, etc. This study can help us to understand and assimilate patterns in the spatiotemporal distribution of ecological water consumption and can provide a basis for the planning and cultivation of forest–meadow vegetation in a region. First, the models of Thornthwaite and Penman-Monteith were used to calculate ecological water consumption. Comparison of the calculation results showed that the data obtained from the Penman-Monteith model were more acceptable, since the model uses a number of meteorological variables and geographic location factors. At the same time, the Jensen formula and the regional soil characteristics curve were used in the calculation of the ecological water consumption to determine the factor for soil moisture correction. Second, the potential evaporation and ecological water consumption of local vegetation was estimated month by month based on precipitation. The spatial and temporal variability of potential values was analyzed on this basis. The results showed that th epotential evaporation tends to increase from month to month from January to July and decrease from August to December. Regarding the spatial distribution, the potential evaporation gradually increases from south to north. The spatial variability of the balance between precipitation and the ecological water consumption of vegetation was analyzed; the results showed that the ecological reserves of water in the central region are more substantial than in the southern region, and the largest reserves of water were found in Yanchi, the northernmost district of the central arid region. Conversely, the ecological water consumption in forests was excessive throughout the growing season in the southernmost district of Jingyuan. In addition, the spatiotemporal variability of the relationship between precipitation-dependent ecological water consumption and water resources is discussed. The results showed that there is still enough space for the regional distribution of vegetation in Yanchi, Tongxin, and Haiyuan in the central arid region and relatively dry districts, such as Yuanzhou, Siji and Pengyang in the southern highlands. More land for an increase in vegetation was observed in the Longde districts and Jingyuan, located in the south of a highland where there is a relatively high amount of precipitation.